Question

我有以下CSV数据

var
  i: Int32;
  stream: TFileStream;
  Path1: string;
  WordApp: TWordApplication;
begin
  Path1 := IncludeTrailingPathDelimiter(GetEnvironmentVariable('TEMP')) +
    FormatDateTime('yyyymmddhhnnssz', Now) + '.doc';
  WordApp := TWordApplication.Create(nil);
  stream := TFileStream.Create(Path1, fmCreate);
  try
    try
      with dm do
      begin
        DataSet.First;
        CopyBlobFieldToStream(dm.DataSet,
          dm.DataSetBlobField, stream);
        ShowMessage(IntToStr(stream.Size));
        DataSet.Next;
        CopyBlobFieldToStream(dm.DataSet,
          dm.DataSetBlobField, stream);
        ShowMessage(IntToStr(stream.Size));
        CopyBlobFieldToStream(dm.DataSet2,
          dm.DataSet2BlobField, stream);
        ShowMessage(IntToStr(stream.Size));
      end;
    finally
      stream.Free;
    end;
    WordApp.Documents.Open(Path1, EmptyParam, False, EmptyParam, EmptyParam,
      EmptyParam, EmptyParam, EmptyParam, EmptyParam, EmptyParam, EmptyParam,
      EmptyParam, EmptyParam, EmptyParam, EmptyParam, EmptyParam);
    WordApp.Visible := True;
  finally
    WordApp.Free;
  end;

前三行是标题。我想要做的是选择第1行和第3行并将其转换为如下所示的数据框：

id,gene,celltype,stem,stem,stem,bcell,bcell,tcell
id,gene,organs,bm,bm,fl,pt,pt,bm
id,gene,organs,stem1,stem2,stem3,b1,b2,t1
134,foo,about_foo,20,10,11,23,22,79
222,bar,about_bar,17,13,55,12,13,88

我坚持以下内容：

Coln1 Coln2
stem  stem1
stem  stem2
stem  stem3
bcell b1
bcell b2
tcell t1

Answer 1

您可以在read_csv中使用参数nrows和skiprows：

import pandas as pd
import io

temp=u"""id,gene,celltype,stem,stem,stem,bcell,bcell,tcell
id,gene,organs,bm,bm,fl,pt,pt,bm
id,gene,organs,stem1,stem2,stem3,b1,b2,t1
134,foo,about_foo,20,10,11,23,22,79
222,bar,about_bar,17,13,55,12,13,88"""

#after testing replace io.StringIO(temp) to filename
df = pd.read_csv(io.StringIO(temp),header=None,index_col=[1,2], nrows=2, skiprows=[1])
df = df.ix[:, 1:].reset_index(drop=True).T
df.columns = ['Coln1', 'Coln2']
print df.reset_index(drop=True)

   Coln1  Coln2
0   stem  stem1
1   stem  stem2
2   stem  stem3
3  bcell     b1
4  bcell     b2
5  tell     t1

要将前3个标题选择为列，请执行以下操作：

df = pd.read_csv(io.StringIO(temp),header=None,index_col=[1,2], nrows=3, skiprows=[4])
df = df.ix[:, 1:].reset_index(drop=True).T
df.columns = ['Coln1', 'Coln2','Coln3']
print df.reset_index(drop=True)

如何将CSV文件的选定标题转换为Pandas数据框

1 个答案: